agentic-paper-digest-skill
matanle51 作
Search & Research概要
Fetches and summarizes recent arXiv.
説明
このスキルでできること
Fetches recent papers from arXiv and Hugging Face, filters them by topic using an LLM relevance classifier, and produces summaries. Runs as a one-off CLI command or a persistent local API server. Results are stored in a SQLite database.
Combines source fetching, LLM-based relevance filtering, and summarization in a single configurable pipeline instead of requiring separate tools for each step.
使いどころ
- Daily digest of new ML/AI papers filtered to your research topics
- Feeding filtered paper metadata into a downstream agent pipeline
- Polling arXiv overnight and saving results for async review
- Tracking papers in specific arXiv categories over a custom time window
- Running a local API so a UI or cron job can query recent papers
ワークフロー例
User asks: Get me today's papers on LLM safety from arXiv
- 1
Bootstrap the repo using the provided bootstrap script
- 2
Set OPENAI_API_KEY in the .env file
- 3
Update config/topics.json with an LLM safety topic entry including relevant keywords
- 4
Run the CLI with --window-hours 24 --sources arxiv
- 5
Read the JSON output for run_id, seen, kept counts and query /api/papers for summaries
A filtered list of arXiv papers matching the LLM safety topic, each with title, abstract summary, and metadata stored in papers.sqlite3
要件
- OPENAI_API_KEY environment variable (or LITELLM_API_KEY with LITELLM_API_BASE for non-OpenAI providers)
インストール
clawhub install matanle51/agentic-paper-digest-skillCLIコマンドを実行するか、Claude Code、Cursor、Codexなどお使いのコーディングエージェントにプロンプトを貼り付けてください。